java爬虫之爬取网页邮箱地址。

爬取本地html中符合正则规范的数据。  要爬取网络 需更换流地址以及正则。

package Socket;

import com.sun.deploy.net.MessageHeader;

import java.io.*;
import java.util.ArrayList;
import java.util.List;
import java.util.regex.Matcher;
import java.util.regex.Pattern;

public class 本地爬虫 {
    public static void main(String[] args) throws IOException {
       List<String> list =  getMails();
       for(String mail:list){
           System.out.println(mail);
       }
    }
    public static List<String> getMails() throws IOException {

        BufferedReader bufferedReader = new BufferedReader(new FileReader("D:\\mails.html"));
        String mail_regex = "\\w+@\\w+(\\.\\w{3})+";
        Pattern pattern = Pattern.compile(mail_regex);
        String line = null;
        List<String> list = new ArrayList<String>();
        while ((line = bufferedReader.readLine())!=null){
            Matcher m = pattern.matcher(line);
            while (m.find()){
              list.add(m.group());
            }
        }

        bufferedReader.close();
        return list;
    }

}